Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers

• URL: http://arxiv.org/abs/2604.12509v1
• Date: Tue, 14 Apr 2026 09:32:24 GMT
• Title: Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers
• Abstract summary: Whole-body controllers (WBCs) can solve problems via hierarchical optimization, but require extensive hand-tuned optimization and remain brittle.<n>We propose WHOLE-MoMa, a two-stage pipeline that first generates diverse demonstrations by randomizing a lightweight WBC.<n>We extend offline implicit Q-learning with Q-chunking for chunk-level critic evaluation and advantage-weighted policy extraction.
• Score: 11.892460841109818
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mobile Manipulation (MoMa) of articulated objects, such as opening doors, drawers, and cupboards, demands simultaneous, whole-body coordination between a robot's base and arms. Classical whole-body controllers (WBCs) can solve such problems via hierarchical optimization, but require extensive hand-tuned optimization and remain brittle. Learning-based methods, on the other hand, show strong generalization capabilities but typically rely on expensive whole-body teleoperation data or heavy reward engineering. We observe that even a sub-optimal WBC is a powerful structural prior: it can be used to collect data in a constrained, task-relevant region of the state-action space, and its behavior can still be improved upon using offline reinforcement learning. Building on this, we propose WHOLE-MoMa, a two-stage pipeline that first generates diverse demonstrations by randomizing a lightweight WBC, and then applies offline RL to identify and stitch together improved behaviors via a reward signal. To support the expressive action-chunked diffusion policies needed for complex coordination tasks, we extend offline implicit Q-learning with Q-chunking for chunk-level critic evaluation and advantage-weighted policy extraction. On three tasks of increasing difficulty using a TIAGo++ mobile manipulator in simulation, WHOLE-MoMa significantly outperforms WBC, behavior cloning, and several offline RL baselines. Policies transfer directly to the real robot without finetuning, achieving 80% success in bimanual drawer manipulation and 68% in simultaneous cupboard opening and object placement, all without any teleoperated or real-world training data.

Related papers

• MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models [55.732137666068446]
  Universal multimodal embedding (UME) increasingly demands encoder's capacity for handling a broad range of tasks and modalities.<n>MoEMB scales UME along the expert axis through mixture-of-experts (MoE)<n>MoEMB surpasses TTE-based methods with >4x active parameters, using significantly less computes.
  arXiv  Detail & Related papers  (2026-09-08T12:29:50Z)
• Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL [11.048264771623836]
  Reinforcement Learning (RL) is essential for robot autonomy, but scaling it to complex tasks is time-consuming and labor-intensive.<n>We show how we can train an off-policy RL agent using purely sparse task rewards, drastically reducing the time required to learn new skills and eliminating the need for manual tuning.<n>We validate the robustness of this framework by successfully deploying complex loco-manipulation skills across different morphologies, including an arm-equipped Spot quadruped and a G1 humanoid.
  arXiv  Detail & Related papers  (2026-08-12T13:48:56Z)
• X-OP: Cross-Morphology Whole-Body Teleoperation via MPC Retargeting [3.134050607080983]
  Whole-body teleoperation is essential for scalable robot data collection in loco-manipulation tasks.<n>We propose a hierarchical whole-body teleoperation framework driven by a single XR device.<n>We show higher success rates on whole-body control tasks for both a humanoid and a mobile manipulator.
  arXiv  Detail & Related papers  (2026-06-06T01:50:59Z)
• ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation [55.467742403416175]
  We introduce a physics-driven neural algorithm that translates large-scale motion capture to humanoid embodiments.<n>We learn a unified multimodal controller that supports both dense references and sparse task specifications.<n>Results show that ULTRA generalizes to autonomous, goal-conditioned whole-body loco-manipulation from egocentric perception.
  arXiv  Detail & Related papers  (2026-03-03T18:59:29Z)
• Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning [49.82882141491629]
  We argue that effective online learning should scale the emphnumber of tasks, rather than the number of samples per task.<n>This regime reveals a structural advantage of model-based reinforcement learning.<n>We instantiate this idea with textbfEfficientZero-Multitask (EZ-M), a sample-efficient multi-task algorithm for online learning.
  arXiv  Detail & Related papers  (2026-03-02T05:07:43Z)
• SOP: A Scalable Online Post-Training System for Vision-Language-Action Models [15.86316960521611]
  Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality.<n>Existing post-training approaches for VLA models are typically offline, single-robot, or task-specific.<n>We introduce a Scalable Online Post-training system that enables online, distributed, multi-task post-training of generalist VLA models directly in the physical world.
  arXiv  Detail & Related papers  (2026-01-06T14:25:11Z)
• CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks [57.95170323315603]
  We introduce CollaPipe, a distributed learning framework that integrates collaborative pipeline parallelism with federated aggregation to support self-evolving networks.<n>In CollaPipe, the encoder part is adaptively partitioned into variable-sized segments and deployed across mobile devices for pipeline-parallel training, while the decoder is deployed on edge servers to handle generative tasks.<n>To enhance training efficiency, we formulate a joint optimization problem that adaptively allocates model segments, micro-batches, bandwidth, and transmission power.
  arXiv  Detail & Related papers  (2025-09-24T07:54:01Z)
• Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids [56.892520712892804]
  We introduce a practical sim-to-real RL recipe that trains a humanoid robot to perform three dexterous manipulation tasks.<n>We demonstrate high success rates on unseen objects and robust, adaptive policy behaviors.
  arXiv  Detail & Related papers  (2025-02-27T18:59:52Z)
• Robotic Control via Embodied Chain-of-Thought Reasoning [86.6680905262442]
  Key limitation of learned robot control policies is their inability to generalize outside their training data.<n>Recent works on vision-language-action models (VLAs) have shown that the use of large, internet pre-trained vision-language models can substantially improve their robustness and generalization ability.<n>We introduce Embodied Chain-of-Thought Reasoning (ECoT) for VLAs, in which we train VLAs to perform multiple steps of reasoning about plans, sub-tasks, motions, and visually grounded features before predicting the robot action.
  arXiv  Detail & Related papers  (2024-07-11T17:31:01Z)
• Generalize by Touching: Tactile Ensemble Skill Transfer for Robotic Furniture Assembly [24.161856591498825]
  Tactile Ensemble Skill Transfer (TEST) is a pioneering offline reinforcement learning (RL) approach that incorporates tactile feedback in the control loop. TEST's core design is to learn a skill transition model for high-level planning, along with a set of adaptive intra-skill goal-reaching policies. Results indicate that TEST can achieve a success rate of 90% and is over 4 times more efficient than the generalization policy.
  arXiv  Detail & Related papers  (2024-04-26T20:27:10Z)
• Bi-Manual Block Assembly via Sim-to-Real Reinforcement Learning [24.223788665601678]
  Two xArm6 robots solve the U-shape assembly task with a success rate of above90% in simulation, and 50% on real hardware without any additional real-world fine-tuning. Our results present a significant step forward for bi-arm capability on real hardware, and we hope our system can inspire future research on deep RL and Sim2Real transfer bi-manualpolicies.
  arXiv  Detail & Related papers  (2023-03-27T01:25:24Z)
• Robot Learning of Mobile Manipulation with Reachability Behavior Priors [38.49783454634775]
  Mobile Manipulation (MM) systems are ideal candidates for taking up the role of a personal assistant in unstructured real-world environments. Among other challenges, MM requires effective coordination of the robot's embodiments for executing tasks that require both mobility and manipulation. We study the integration of robotic reachability priors in actor-critic RL methods for accelerating the learning of MM for reaching and fetching tasks.
  arXiv  Detail & Related papers  (2022-03-08T12:44:42Z)
• Whole-Body Control of a Mobile Manipulator using End-to-End Reinforcement Learning [31.150823782805283]
  We propose an end-to-end Reinforcement Learning (RL) approach to Whole-Body Control (WBC) We compared our learned controller against a state-of-the-art sampling-based method in simulation and achieved faster overall mission times.
  arXiv  Detail & Related papers  (2020-02-25T21:21:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.